레이저 열화상 기법과 CNN 딥러닝을 이용한 용접부 표면의 자동 균열 검출 기술 개발

국문 초록 (Abstract)

본 연구에서는 레이저 열화상 시스템과 균열 검출 알고리즘 개발을 통해 용접부에서 균열을 자동검출하는 기술을 연구하였다. 레이저 열화상 시스템은 레이저 가진으로 인해 균열부에서 발생하는 열파 집중현상을 관측하도록 구성되었다. 균열 검출 알고리즘은 (1) 온도 분포 특성을 이용한 열화상 이미지 병합으로 균열을 가시화하고, (2) 과적합을 방지하는 input 이미지 생성과 (3) CNN 딥러닝을 통해 균열부의 특징을 분석, 분류하여, (4) 원본 열화상 이미지에 균열의 위치를 Masking 한다. SUS 시험편 2개로 개발 기술을 검증하였고, 현미경과 액체침투법으로 확인한 실제 균열 정보와 비교하였다. 시험편 #1의 균열 이미지 618 개와 정상 이미지 1834개로 CNN 을 훈련시켰다. 시험편 #1과 #2의 총 9개 영역을 각 300개의 Test 이미지로 나눠 훈련된 알고리즘 성능을 검증해본 결과, 총 균열 14개 중 13개를 검출하였고, 정상 이미지 4개가 과검출되었다. 따라서 개발된 알고리즘은 용접부에서 용접의 복잡한 패턴과 구별하여 균열을 검출할 수 있다.

다국어 초록 (Multilingual Abstract)

In this study, automatic crack detection for welded surfaces was studied through the development of a laser active thermography system and a crack detection algorithm. The laser active thermography system observes thermal wave concentrations in the crack while exciting the surface of the weld. The crack detection algorithm (1) visualizes the cracks by merging the infrared (IR) images using the temperature distribution characteristics; (2) employs input image generation with a specific method to prevent overfitting; (3) analyzes and classifies the characteristics of the cracks using a deep learning convolutional neural network (CNN); and (4) marks the location of the cracks in the original IR image. The system and algorithm were verified using two SUS specimens (#1 and #2) and compared with actual crack data obtained by microscopy and penetration test. The CNN was trained with 618 images of cracks and 1834 images of intact specimen #1. For performance verification, a total of nine areas of specimens #1 and #2 were divided into 300 test images; 13 out of 14 cracks were detected while four intact images were overdetected. Thus, the developed algorithm can detect cracks in welded surfaces by distinuishing them from complex patterns of welding.

목차 (Table of Contents)

• 초록
• Abstract
• 1. 서론
• 2. 이론적 배경
• 3. 균열 검출 알고리즘 개발
• 4. 실험 검증
• 5. 결론
• References

참고문헌 (Reference)

• 1 SD. Holland, "Thermographic signal reconstruction for vibrothermography" 54 (54): 503-511, 2011
• 2 G. Zenzinger, "Thermographic crack detection by eddy current excitation" 22 (22): 101-111, 2007
• 3 R. Mulaveesala, "Theory of frequency modulated thermal wave imaging for nondestructive subsurface defect detection" 89 (89): 191913-, 2006
• 4 P. Broberg, "Surface crack detection in welds using thermography" 57 : 69-73, 2013
• 5 L. Cheng, "Surface crack detection for carbon fiber reinforced plastic(CFRP)materials using pulsed eddy current thermography" 11 (11): 3261-3268, 2011
• 6 H. J. Lim, "Reference-free fatigue crack detection using nonlinear ultrasonic modulation under various temperature and loading conditions" 45 (45): 468-478, 2014
• 7 M. Choi, "Quantitative determination of a subsurface defect of reference specimen by lock-in infrared thermography" 41 (41): 119-124, 2008
• 8 XV. Maldague, "Pulse phase infrared thermography" 79 (79): 2694-2698, 1996
• 9 M. Morbidini, "Prediction of the thermosonic signal from fatigue cracks in metals using vibration damping measurements" 100 (100): 104905-, 2006
• 10 J-M. Piau, "Nondestructive testing of open microscopic cracks in plasma-sprayed-coatings using ultrasound excited vibrothermography" 23 (23): 109-120, 2008
• 11 J. Cheng, "Monitoring fatigue crack growth using nonlinear ultrasonic phased array imaging" 26 (26): 055006-, 2010
• 12 S. Hwang, "Monitoring and instantaneous evaluation of fatigue crack using integrated passive and active laser thermography" 119 : 9-17, 2019
• 13 CB. Scruby, "Laser ultrasonics:techniques and applications" Taylor & Francis 1990
• 14 VS. Ghali, "Frequency-modulated thermal wave imaging for non-destructive testing of carbon fiber-reinforced plastic materials" 22 (22): 104018-, 2011
• 15 N. Biju, "Frequency optimization for eddy current thermography" 42 (42): 415-420, 2009
• 16 H. Li, "Estimation and warning of fatigue damage of FRP stay cables based on acoustic emission techniques and fractal theory" 26 (26): 500-512, 2011
• 17 F. C. Campbell, "Elements of metallurgy and engineering alloys" ASM International 2008
• 18 D. A. Cook, "Detection of small surface-breaking fatigue cracks in steel using scattering of Rayleigh waves" 34 (34): 483-492, 2001
• 19 P. Umesha, "Crack detection and quantification in beams using wavelets" 24 (24): 593-607, 2009
• 20 S. B. Kim, "Continuous fatigue crack monitoring without baseline data" 31 (31): 644-659, 2008
• 21 M. Ryles, "Comparative study of nonlinear acoustic and Lamb wave techniques for fatigue crack detection in metallic structures" 31 (31): 674-683, 2008
• 22 XV. Maldague, "Advances in pulsed phase thermography" 43 (43): 175-181, 2002
• 23 A. Nair, "Acoustic emission monitoring of bridges : Review and case studies" 32 (32): 1704-1714, 2010
• 24 N. Nemati, "Acoustic emission assessment of through-thickness fatigue crack growth in steel members" 18 (18): 269-282, 2015
• 25 K. Chatterjee, "A comparison of the pulsed, lock-in and frequency modulated thermography nondestructive evaluation techniques" 44 (44): 655-667, 2011